On Model Adaptation for Sensorimotor Control of Robots
This addresses the challenge of robotic adaptation in sensorimotor control for tasks like manipulation with uncalibrated sensors, but appears incremental as it builds on existing computational methods.
The paper tackles the problem of computing adaptive sensorimotor models for robotic control under uncertain action-to-perception relations, resulting in a methodology applied to shape control of deformable objects and soft manipulation of ultrasonic probes.
In this article, we address the problem of computing adaptive sensorimotor models that can be used for guiding the motion of robotic systems with uncertain action-to-perception relations. The formulation of the uncalibrated sensor-based control problem is first presented, then, various computational methods for building adaptive sensorimotor models are derived and analysed. The proposed methodology is exemplified with two cases of study: (i) shape control of deformable objects with unknown properties, and (ii) soft manipulation of ultrasonic probes with uncalibrated sensors.